Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to common practices or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific practices or behaviors, particularly those that are controversial or criticized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gin
    -0.78
    itialized
    -0.76
    ilee
    -0.73
     juven
    -0.71
    aline
    -0.71
    éĹĺ
    -0.69
     raspberry
    -0.67
    gow
    -0.67
    worms
    -0.66
    onge
    -0.65
    POSITIVE LOGITS
    ually
    0.92
     Practices
    0.78
     practiced
    0.78
     practices
    0.77
    uality
    0.76
     practice
    0.74
     pract
    0.70
    itual
    0.68
     practitioners
    0.67
    reating
    0.66
    Act Density 0.023%

    No Known Activations